vos-data-utils 0.0.2__py3-none-any.whl → 0.0.4__py3-none-any.whl

vdutils/convaddr.py

@@ -1,4 +1,5 @@
 import re
+import pkg_resources
 import pandas as pd
 from typing import (
     List,
@@ -6,15 +7,41 @@ from typing import (
     Optional
 )
 from dataclasses import dataclass
-from vdutils import Log
-from vdutils.bjd import Bjd
+from vdutils.library import Log
+from vdutils.data import (
+    __sep__,
+    __index__,
+    __encoding__,
+    _get_folder_names
+)
 
 
 @dataclass
 class ConvAddr():
 
 
-    def __init__(self):
+    def __init__(
+        self,
+        base_dt: Optional[str] = None,
+        is_inherit: bool = False
+    ):
+
+        if base_dt is not None:
+            if not isinstance(base_dt, str):
+                raise TypeError("type of object('base_dt') must be string")
+
+            if not base_dt.isdigit():
+                raise ValueError("object('base_dt') should be a string consisting of numbers")
+
+            if len(base_dt) != 8:
+                raise ValueError("object('base_dt') should be a string consisting of exactly 8(YYYYMMDD) digits")
+        else: pass
+
+        self.sep = __sep__
+        self.index = __index__
+        self.encoding = __encoding__
+        self.base_dt: str = base_dt
+        self.is_inherit: bool = is_inherit
         self.bjd_current_dic: Dict[str, str] = None
         self.bjd_smallest_list: List[str] = None
         self.bjd_current_bjd_nm_list: List[str] = None
@@ -27,7 +54,77 @@ class ConvAddr():
         self.bjd_changed_dic: Dict[str, str] = None
         self.bjd_changed_old_bjd_nm_list: List[str] = None
         self.logger = Log('ConvertAddress').stream_handler("INFO")
+        self._get_base_dt()
+        self._get_file_names()
         self._prepare()
+        self.base_dt_print: str = f"{self.base_dt[:4]}-{self.base_dt[4:6]}-{self.base_dt[6:8]}"
+
+
+    def _find_latest_base_dt(
+        self,
+        base_dts: List[str]
+    ) -> str:
+
+        """
+        입력된 날짜(YYYYMMDD)와 법정동 데이터 시점 리스트와 비교하여 입력된 날짜보다 과거 시점 중 최신 시점을 반환
+        """
+
+        for date in base_dts:
+            if date < self.base_dt:
+                return date
+
+        # 입력된 날짜보다 작은 날짜가 없을 경우
+        self.logger.info("입력된 날짜보다 이전 시점의 법정동 데이터가 존재하지 않습니다. 보유한 데이터중 최신 데이터를 적용합니다.")
+        return base_dts[0]
+
+
+    def _get_base_dt(self):
+
+        """
+        입력된 날짜(YYYYMMDD)와 법정동 데이터 시점 리스트와 비교하여 입력된 날짜보다 과거 시점 중 최신 시점을 반환 \n
+        입력된 날짜(YYYYMMDD)가 없으면 데이터 시점 리스트 중 최신 시점을 반환
+        """
+
+        if self.is_inherit:
+            return self.base_dt
+
+        base_dts = _get_folder_names(base_folder_path='vdutils/data/bjd')
+        base_dts = sorted(base_dts, reverse=True)
+        try:
+            if self.base_dt is None:
+                self.base_dt = base_dts[0]
+            else:
+                self.base_dt = self._find_latest_base_dt(base_dts=base_dts)
+        finally:
+            self.logger.info(f"적용 법정동 데이터 시점: {self.base_dt}")
+
+
+    def _get_file_names(self):
+        self.file_name_bjd = pkg_resources.resource_filename(
+            "vdutils", 
+            f"data/bjd/{self.base_dt}/bjd.txt"
+        )
+        self.file_name_bjd_current = pkg_resources.resource_filename(
+            "vdutils", 
+            f"data/bjd/{self.base_dt}/bjd_current.txt"
+        )
+        self.file_name_bjd_changed = pkg_resources.resource_filename(
+            "vdutils", 
+            f"data/bjd/{self.base_dt}/bjd_changed.txt"
+        )
+        self.file_name_bjd_smallest = pkg_resources.resource_filename(
+            "vdutils", 
+            f"data/bjd/{self.base_dt}/bjd_smallest.txt"
+        )
+        self.file_name_bjd_frequency_dictionary = pkg_resources.resource_filename(
+            "vdutils", 
+            f"data/bjd/{self.base_dt}/bjd_frequency_dictionary.txt"
+        )
+        self.file_name_multiple_word_sgg_list = pkg_resources.resource_filename(
+            "vdutils", 
+            f"data/bjd/{self.base_dt}/multiple_word_sgg_list.txt"
+        )
+
 
     @staticmethod
     def _concat_sido_sgg(
@@ -41,6 +138,7 @@ class ConvAddr():
         else:
             return None
 
+
     def _create_bjd_changed_dictionary(
         self,
         bjd_changed_df: pd.DataFrame
@@ -59,32 +157,23 @@ class ConvAddr():
                 bjd_changed_dictionary[old_bjd_nm] = new_bjd_nm
         return bjd_changed_dictionary
 
+
     def _prepare(self):
-        cls_bjd = Bjd()
-        file_name_bjd: str = cls_bjd.file_name_bjd
-        file_name_bjd_current: str = cls_bjd.file_name_bjd_current
-        file_name_bjd_changed: str = cls_bjd.file_name_bjd_changed
-        file_name_bjd_smallest: str = cls_bjd.file_name_bjd_smallest
-        file_name_bjd_frequency_dictionary: str = cls_bjd.file_name_bjd_frequency_dictionary
-        file_name_multiple_word_sgg_list: str = cls_bjd.file_name_multiple_word_sgg_list
-        input_encoding = cls_bjd.output_encoding
-        input_index = cls_bjd.output_index
-        input_sep = cls_bjd.output_sep
-
-        with open(file_name_bjd_current, 'r') as file_bjd_current:
+
+        with open(self.file_name_bjd_current, 'r') as file_bjd_current:
             self.bjd_current_dic: Dict[str, str] = dict((line.split('\t')[2], line.split('\t')[9].replace('\n', '')) for line in file_bjd_current)
 
-        with open(file_name_bjd_smallest, 'r') as file_bjd_smallest:
+        with open(self.file_name_bjd_smallest, 'r') as file_bjd_smallest:
             self.bjd_smallest_list: List[str] = [line.strip() for line in file_bjd_smallest]
 
-        with open(file_name_multiple_word_sgg_list, 'r') as file_multiple_word_sgg_list:
+        with open(self.file_name_multiple_word_sgg_list, 'r') as file_multiple_word_sgg_list:
             self.multiple_word_sgg_list: List[str] = [line.strip() for line in file_multiple_word_sgg_list]
 
         bjd_df: pd.DataFrame = pd.read_csv(
-            file_name_bjd,
-            sep=input_sep,
+            self.file_name_bjd,
+            sep=self.sep,
             engine='python',
-            encoding=input_encoding,
+            encoding=self.encoding,
             dtype={
                 '과거법정동코드': str,
                 '법정동코드': str
@@ -96,10 +185,11 @@ class ConvAddr():
         self.ri_list: List[str] = list(ri for ri in bjd_df['리명'].unique() if isinstance(ri, str))
 
         bjd_current_df: pd.DataFrame = pd.read_csv(
-            file_name_bjd_current,
-            sep=input_sep,
+            self.file_name_bjd_current,
+            sep=self.sep,
             engine='python',
-            encoding=input_encoding)
+            encoding=self.encoding
+        )
         self.bjd_current_bjd_nm_list: List[str] = list(bjd_nm for bjd_nm in bjd_current_df['법정동명'] if bjd_nm is not None)
         bjd_current_df['시도시군구명'] = bjd_current_df[['시도명', '시군구명']].apply(lambda x: self._concat_sido_sgg(*x), axis=1)
         self.current_sido_sgg_list: List[str] = list(sido_sgg for sido_sgg in bjd_current_df['시도시군구명'].unique() if isinstance(sido_sgg, str))
@@ -110,10 +200,10 @@ class ConvAddr():
         self.bjd_current_df = bjd_current_df
 
         bjd_changed_df: pd.DataFrame = pd.read_csv(
-            file_name_bjd_changed,
-            sep=input_sep,
+            self.file_name_bjd_changed,
+            sep=self.sep,
             engine='python',
-            encoding=input_encoding,
+            encoding=self.encoding,
             dtype={
                 '과거법정동코드': str,
                 '법정동코드': str
@@ -125,6 +215,7 @@ class ConvAddr():
         self.bjd_changed_dic: Dict[str, str] = self._create_bjd_changed_dictionary(sub_bjd_changed_df)
         self.bjd_changed_old_bjd_nm_list: List[str] = list(self.bjd_changed_dic.keys())
 
+
     @staticmethod
     def correct_simple_spacing(
         addr: str
@@ -148,6 +239,7 @@ class ConvAddr():
 
         return re.sub(r'\s+', ' ', addr)
 
+
     # 가장 작은 법정동명 뒤 번지가 띄어쓰기 없이 붙어있을 경우,
     # 가장 작은 법정동명에 포함된 숫자중 2자리수는 없음. 예 당산동1가, 을지로5가 등
     def correct_smallest_bjd_spacing(
@@ -181,6 +273,7 @@ class ConvAddr():
                 return addr
         return addr
 
+
     @staticmethod
     def union_similar_changed_bjd(
         changed_bjd_list: List[str]
@@ -199,6 +292,7 @@ class ConvAddr():
         else:
             return changed_bjd_list
 
+
     def correct_changed_bjd(
         self,
         addr: str,
@@ -249,6 +343,7 @@ class ConvAddr():
 
         return addr
 
+
     def correct_bjd(
         self,
         addr: str,

vdutils/cordate.py

@@ -19,7 +19,7 @@ class CorDate():
         self.sym_spell = SymSpell()
         self.dictionary_path = pkg_resources.resource_filename(
             "vdutils", 
-            "data/date_dictionary.txt"
+            "data/date/date_dictionary.txt"
         )
         self.this_year: int = datetime.now().year
         self.this_year_two_length: int = int(str(self.this_year)[2:])

vdutils/data/__init__.py

@@ -1,13 +1,14 @@
 import os
-import pickle
+from typing import (
+    List
+)
 
 
-def get_data_from_pnu(file_name):
-    data_dir_path = os.path.abspath(__file__).replace("__init__.py", '')
-    data_file_path = f"{data_dir_path}/pnu/{file_name}"
-    with open(data_file_path, "rb") as f:
-        return pickle.load(f)
+__sep__ = '\t'
+__encoding__: str = 'utf-8'
+__index__: bool = False
 
-def get_files_from_pnu():
-    data_dir_path = os.path.abspath(__file__).replace("__init__.py", '')
-    return os.listdir(f"{data_dir_path}/pnu")
+def _get_folder_names(
+    base_folder_path: str
+) -> List[str]:
+    return [f.name for f in os.scandir(base_folder_path) if f.is_dir()]